Add a MySQL backup helper

.gitignore

@@ -14,3 +14,4 @@
 
 __pycache__
 /datman-helper-postgres/datman_helper_postgres.egg-info
+/datman-helper-mysql/datman_helper_mysql.egg-info

.woodpecker.yml

@@ -20,16 +20,17 @@ pipeline:
   testSuite:
     image: rust:1.54.0-slim-bullseye
     commands:
-      - apt-get -qq update && apt-get -yqq install pkg-config libssl-dev build-essential libsqlite3-dev python3.9 python3.9-venv postgresql postgresql-client
+      - apt-get -qq update && apt-get -yqq install pkg-config libssl-dev build-essential libsqlite3-dev python3.9 python3.9-venv postgresql postgresql-client mariadb-server mariadb-client
       - pg_ctlcluster 13 main start
       - su postgres -c 'createuser root'
       - su postgres -c 'createdb -O root testsuitedb'
       - psql testsuitedb -c 'CREATE TABLE testsuitetable ();'
+      - mysql -e 'CREATE DATABASE testsuitemydb; USE testsuitemydb; CREATE TABLE sometable (INT PRIMARY KEY); INSERT INTO sometable VALUES (42);'
       - cargo install -q --path yama
       - cargo install -q --path datman
       - python3.9 -m venv testsuite/.venv
-      - ./testsuite/.venv/bin/pip install -e testsuite -e datman-helper-postgres
-      - cd testsuite && TEST_POSTGRES=$(hostname),testsuitedb,root ./.venv/bin/green
+      - ./testsuite/.venv/bin/pip install -e testsuite -e datman-helper-postgres -e datman-helper-mysql
+      - cd testsuite && . .venv/bin/activate && TEST_POSTGRES=$(hostname),testsuitedb,root TEST_MYSQL=$(hostname),testsuitemydb,root green
 
   deployManual:
     image: rust:1.54.0-slim

datman-helper-mysql/datman_helper_mysql/backup.py

@@ -0,0 +1,86 @@
+import json
+import os
+import pwd
+import subprocess
+import sys
+
+
+def cli():
+    """
+    Performs a backup of a MySQL database.
+
+    Parameters:
+        database: str — the name of the database to back up.
+
+        user: optional str — the name of the Linux user to use to connect to MySQL.
+            Sudo or SSH will be used to make this happen, if it's specified,
+            unless it's a local user that is already the current user.
+
+        host: optional str — if specified, the backup will be made using SSH
+        (unless this host is the same as the one named)
+    """
+    request_info = json.load(sys.stdin)
+    assert isinstance(request_info, dict)
+
+    database_to_use = request_info["database"]
+    user_to_use = request_info.get("user")
+    host_to_use = request_info.get("host")
+    use_lz4 = request_info.get("use_lz4_for_ssh", True)
+
+    if host_to_use is not None:
+        hostname = subprocess.check_output("hostname").decode().strip()
+        if hostname == host_to_use:
+            host_to_use = None
+
+    command = []
+
+    if host_to_use is not None:
+        command.append("ssh")
+        if user_to_use is not None:
+            command.append(f"{user_to_use}@{host_to_use}")
+        else:
+            command.append(f"{host_to_use}")
+    elif user_to_use is not None:
+        current_username = pwd.getpwuid(os.getuid()).pw_name
+        if current_username != user_to_use:
+            command.append("sudo")
+            command.append("-u")
+            command.append(user_to_use)
+
+    command.append("mysqldump")
+    command.append(database_to_use)
+
+    # Where the output of the dump command should go.
+    output_of_dump = sys.stdout
+    # The process (if any) that is our LZ4 decompressor.
+    lz4_process = None
+
+    if use_lz4 and host_to_use is not None:
+        # Add an LZ4 compressor on the remote side.
+        command += ["|", "lz4", "--compress", "--stdout"]
+
+        # Then open an LZ4 decompressor on our side.
+        lz4_process = subprocess.Popen(
+            ["lz4", "--decompress", "--stdout"],
+            stdin=subprocess.PIPE,
+            stdout=sys.stdout,
+            stderr=sys.stderr,
+        )
+        output_of_dump = lz4_process.stdin
+
+    # we MUST disable shell here otherwise the local side will do both
+    # the compression and decompression which would be silly!
+    subprocess.check_call(
+        command,
+        stdin=subprocess.DEVNULL,
+        stdout=output_of_dump,
+        stderr=sys.stderr,
+        shell=False,
+    )
+
+    if lz4_process is not None:
+        # must close here, otherwise the decompressor never ends
+        lz4_process.stdin.close()
+        exit_code = lz4_process.wait()
+        if exit_code != 0:
+            raise ChildProcessError(f"lz4 not happy: {exit_code}")

datman-helper-mysql/setup.py

@@ -0,0 +1,119 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+import io
+import os
+import sys
+from shutil import rmtree
+
+from setuptools import Command, find_packages, setup
+
+# Package meta-data.
+NAME = "datman_helper_mysql"
+DESCRIPTION = "MySQL integration for Datman"
+URL = "https://bics.ga/reivilibre/yama"
+EMAIL = "reivi@librepush.net"
+AUTHOR = "Olivier 'reivilibre'"
+REQUIRES_PYTHON = ">=3.7.0"
+VERSION = "0.1.0"
+
+# What packages are required for this module to be executed?
+REQUIRED = []
+
+
+# What packages are optional?
+EXTRAS = {}
+
+# The rest you shouldn't have to touch too much :)
+# ------------------------------------------------
+# Except, perhaps the License and Trove Classifiers!
+# If you do change the License, remember to change the Trove Classifier for that!
+
+here = os.path.abspath(os.path.dirname(__file__))
+
+# Import the README and use it as the long-description.
+# Note: this will only work if 'README.md' is present in your MANIFEST.in file!
+try:
+    with io.open(os.path.join(here, "README.md"), encoding="utf-8") as f:
+        long_description = "\n" + f.read()
+except FileNotFoundError:
+    long_description = DESCRIPTION
+
+# Load the package's __version__.py module as a dictionary.
+about = {}
+if not VERSION:
+    project_slug = NAME.lower().replace("-", "_").replace(" ", "_")
+    with open(os.path.join(here, project_slug, "__version__.py")) as f:
+        exec(f.read(), about)
+else:
+    about["__version__"] = VERSION
+
+
+class UploadCommand(Command):
+    """Support setup.py upload."""
+
+    description = "Build and publish the package."
+    user_options = []
+
+    @staticmethod
+    def status(s):
+        """Prints things in bold."""
+        print("\033[1m{0}\033[0m".format(s))
+
+    def initialize_options(self):
+        pass
+
+    def finalize_options(self):
+        pass
+
+    def run(self):
+        try:
+            self.status("Removing previous builds…")
+            rmtree(os.path.join(here, "dist"))
+        except OSError:
+            pass
+
+        self.status("Building Source and Wheel (universal) distribution…")
+        os.system("{0} setup.py sdist bdist_wheel --universal".format(sys.executable))
+
+        self.status("Uploading the package to PyPI via Twine…")
+        os.system("twine upload dist/*")
+
+        self.status("Pushing git tags…")
+        os.system("git tag v{0}".format(about["__version__"]))
+        os.system("git push --tags")
+
+        sys.exit()
+
+
+# Where the magic happens:
+setup(
+    name=NAME,
+    version=about["__version__"],
+    description=DESCRIPTION,
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    author=AUTHOR,
+    author_email=EMAIL,
+    python_requires=REQUIRES_PYTHON,
+    url=URL,
+    packages=find_packages(exclude=["tests", "*.tests", "*.tests.*", "tests.*"]),
+    # If your package is a single module, use this instead of 'packages':
+    # py_modules=['mypackage'],
+    entry_points={
+        "console_scripts": [
+            "datman-helper-postgres-backup=datman_helper_postgres.backup:cli",
+            "datman-helper-postgres-restore=datman_helper_postgres.restore:cli",
+        ],
+    },
+    install_requires=REQUIRED,
+    extras_require=EXTRAS,
+    include_package_data=True,
+    # TODO license='GPL3',
+    classifiers=[
+        # Trove classifiers
+        # Full list: https://pypi.python.org/pypi?%3Aaction=list_classifiers
+        "Programming Language :: Python",
+        "Programming Language :: Python :: 3",
+    ],
+)

scripts-dev/lint.sh

@@ -4,7 +4,7 @@ if [ $# -ge 1 ]
 then
   files=$*
 else
-  files="testsuite/setup.py testsuite/datmantests testsuite/helpers testsuite/yamatests datman-helper-postgres/datman_helper_postgres datman-helper-postgres/setup.py"
+  files="testsuite/setup.py testsuite/datmantests testsuite/helpers testsuite/yamatests datman-helper-postgres/datman_helper_postgres datman-helper-postgres/setup.py datman-helper-mysql/datman_helper_mysql datman-helper-mysql/setup.py"
 fi
 
 echo "Linting these locations: $files"

testsuite/datmantests/test_mysql_helper.py

@@ -0,0 +1,108 @@
+import json
+import os
+import subprocess
+from pathlib import Path
+from tempfile import TemporaryDirectory
+from unittest import TestCase
+
+from helpers import DirectoryDescriptor, scan_dir
+from helpers.datman_helpers import set_up_simple_datman
+from helpers.yama_helpers import set_up_simple_yama
+
+
+class TestPostgresHelper(TestCase):
+    def setUp(self):
+        if "TEST_MYSQL" not in os.environ:
+            self.skipTest(
+                "TEST_MYSQL environment variable not set. "
+                "Should be set to a MySQL host, database,"
+                " user combination, comma-separated."
+            )
+
+    def test_helper_fails_on_bad_connection(self):
+        proc = subprocess.Popen("datman-helper-mysql-backup", stdin=subprocess.PIPE)
+        proc.stdin.write(
+            json.dumps(
+                {"database": "mydatabase", "host": "notmyhost", "user": "bobjones"}
+            ).encode()
+        )
+        proc.stdin.close()
+        self.assertNotEqual(proc.wait(), 0)
+
+    def test_helper_succeeds_on_correct_config(self):
+        my_host, my_database, my_user = os.environ["TEST_MYSQL"].split(",")
+
+        proc = subprocess.Popen(
+            "datman-helper-mysql-backup",
+            stdin=subprocess.PIPE,
+            stdout=subprocess.PIPE,
+        )
+        proc.stdin.write(
+            json.dumps(
+                {
+                    "database": my_database or None,
+                    "host": my_host or None,
+                    "user": my_user or None,
+                }
+            ).encode()
+        )
+        proc.stdin.close()
+        stdout = proc.stdout.read()
+        self.assertEqual(proc.wait(), 0)
+        self.assertIn(b"CREATE TABLE", stdout)
+        self.assertIn(b"INSERT INTO", stdout)
+        print(stdout) # TODO
+
+    def test_backup_and_extraction(self):
+        td = TemporaryDirectory("test_my_bae")
+        tdpath = Path(td.name)
+
+        my_host, my_database, my_user = os.environ["TEST_MYSQL"].split(",")
+
+        datman_path = tdpath.joinpath("datman")
+        yama_path = datman_path.joinpath("main")
+
+        set_up_simple_datman(
+            datman_path,
+            custom_extra_test=f"""
+[source.mysql123]
+helper = "mysql"
+label = "precious"
+kind = {{ stdout = "mysql123.sql" }}
+database = "{my_database}"
+host = "{my_host}"
+user = "{my_user}"
+        """,
+        )
+        set_up_simple_yama(yama_path)
+
+        print("storing")
+        subprocess.check_call(
+            ("datman", "backup-one", "mysql123", "main"), cwd=datman_path
+        )
+
+        print("extracting")
+        dest_path = tdpath.joinpath("desta")
+        subprocess.check_call(
+            (
+                "datman",
+                "extract",
+                "--skip-metadata",
+                "--accept-partial",
+                "main",
+                "../desta",
+            ),
+            cwd=datman_path,
+        )
+
+        # this will be wrapped in a directory that starts with the name postgres123+
+        extracted_dir_descriptor_wrapper = scan_dir(dest_path)
+
+        contents = extracted_dir_descriptor_wrapper.contents
+        self.assertEqual(len(contents), 1)
+        key, value = next(iter(contents.items()))
+        self.assertTrue(key.startswith("mysql123+"))
+
+        self.assertIsInstance(value, DirectoryDescriptor)
+        key, value = next(iter(value.contents.items()))
+        self.assertEqual(key, "mysql123.sql")